--- title: acge_text_embedding canonical_url: "https://www.modelscope.cn/models/yangjhchs/acge_text_embedding" md_url: "https://www.modelscope.cn/models/yangjhchs/acge_text_embedding.md" repository: yangjhchs/acge_text_embedding last_updated: 2024-04-10 pipeline_tag: sentence-similarity tasks: - sentence-similarity model_type: - bert architectures: - BertModel parameters: 327.9M tensor_type: - BF16 - I64 library_name: - pytorch - sentence-transformers - safetensors frameworks: - Pytorch inference_backends: - "deploy_task emb" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 330303 stars: 14 tags: - mteb - sentence-transformers - feature-extraction - sentence-similarity --- # acge_text_embedding > acge_text_embedding - yangjhchs 在 ModelScope 开源的模型。从https://huggingface.co/aspire/acge_text_embedding搬迁过来 yangjhchs/acge_text_embedding 是 ModelScope 魔搭社区上的 327.9M 参数sentence-similarity模型，可用 deploy_task emb、sglang 0.5.2、vllm 0.9.2 部署。 - **Repository**: yangjhchs/acge_text_embedding - **Tasks**: sentence-similarity - **Parameters**: 327.9M - **Inference backends**: deploy_task emb, sglang 0.5.2, vllm 0.9.2 - **Tags**: mteb, sentence-transformers, feature-extraction, sentence-similarity - **Downloads**: 330303 - **Stars**: 14 - **Last updated**: 2024-04-10 Source: https://www.modelscope.cn/models/yangjhchs/acge_text_embedding --- # **以下内容同HuggingFace，仅用于方便国内用户下载使用，仅个人出于方便使用目的上传，如有侵权立刻删除。[官方地址](https://huggingface.co/aspire/acge_text_embedding)**
icon
## acge model acge模型来自于[合合信息](https://www.intsig.com/)技术团队，对外技术试用平台[TextIn](https://www.textin.com/)。合合信息是行业领先的人工智能及大数据科技企业，致力于通过智能文字识别及商业大数据领域的核心技术、C端和B端产品以及行业解决方案为全球企业和个人用户提供创新的数字化、智能化服务。 技术交流请联系，商务合作请联系，可以[点击图片](https://huggingface.co/aspire/acge_text_embedding/blob/main/img/wx.jpg)，扫面二维码来加入我们的微信社群。想加入合合信息，做“文档解析”、“文档检索”、“文档预研”的同学可以投简历给min_du@intsig.net，也可直接添加[HR微信](https://huggingface.co/aspire/acge_text_embedding/blob/main/img/hr.jpg)详聊岗位内容。 acge是一个通用的文本编码模型，是一个可变长度的向量化模型，使用了[Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147)，如图所示： ![matryoshka-small](./img/matryoshka-small.gif) 建议使用的维度为1024或者1792 | Model Name | Model Size (GB) | Dimension | Sequence Length | Language | Need instruction for retrieval? | |:------------------:|:---------------:|:---------:|:---------------:|:--------:|:-------------------------------:| | acge-text-embedding | 0.65 | [1024, 1792] | 1024 | Chinese | NO | ## Metric #### C-MTEB leaderboard (Chinese) 测试的时候因为数据的随机性、显卡、推理的数据类型导致每次推理的结果不一致，我总共测试了4次，不同的显卡(A10 A100)，不同的数据类型，测试结果放在了result文件夹中，选取了一个精度最低的测试作为最终的精度测试。 根据[infgrad](https://huggingface.co/infgrad)的建议，选取不用的输入的长度作为测试，Sequence Length为512时测试最佳。 | Model Name | GPU | tensor-type | Model Size (GB) | Dimension | Sequence Length | Average (35) | Classification (9) | Clustering (4) | Pair Classification (2) | Reranking (4) | Retrieval (8) | STS (8) | |:------------------:|:---------------:|:---------:|:---------------:|:------------:|:------------------:|:--------------:|:-----------------------:|:-------------:|:-------------:|:-------:|:-------:|:-------:| | acge_text_embedding | NVIDIA TESLA A10 | bfloat16 | 0.65 | 1792 | 1024 | 68.91 | 72.76 | 58.22 | 87.82 | 67.67 | 72.48 | 62.24 | | acge_text_embedding | NVIDIA TESLA A100 | bfloat16 | 0.65 | 1792 | 1024 | 68.91 | 72.77 | 58.35 | 87.82 | 67.53 | 72.48 | 62.24 | | acge_text_embedding | NVIDIA TESLA A100 | float16 | 0.65 | 1792 | 1024 | 68.99 | 72.76 | 58.68 | 87.84 | 67.89 | 72.49 | 62.24 | | acge_text_embedding | NVIDIA TESLA A100 | float32 | 0.65 | 1792 | 1024 | 68.98 | 72.76 | 58.58 | 87.83 | 67.91 | 72.49 | 62.24 | | acge_text_embedding | NVIDIA TESLA A100 | float16 | 0.65 | 1792 | 768 | 68.95 | 72.76 | 58.68 | 87.84 | 67.86 | 72.48 | 62.07 | | acge_text_embedding | NVIDIA TESLA A100 | float16 | 0.65 | 1792 | 512 | 69.07 | 72.75 | 58.7 | 87.84 | 67.99 | 72.93 | 62.09 | #### Reproduce our results **C-MTEB:** ```python import torch import argparse import functools from C_MTEB.tasks import * from typing import List, Dict from sentence_transformers import SentenceTransformer from mteb import MTEB, DRESModel class RetrievalModel(DRESModel): def __init__(self, encoder, **kwargs): self.encoder = encoder def encode_queries(self, queries: List[str], **kwargs) -> np.ndarray: input_texts = ['{}'.format(q) for q in queries] return self._do_encode(input_texts) def encode_corpus(self, corpus: List[Dict[str, str]], **kwargs) -> np.ndarray: input_texts = ['{} {}'.format(doc.get('title', ''), doc['text']).strip() for doc in corpus] input_texts = ['{}'.format(t) for t in input_texts] return self._do_encode(input_texts) @torch.no_grad() def _do_encode(self, input_texts: List[str]) -> np.ndarray: return self.encoder.encode( sentences=input_texts, batch_size=512, normalize_embeddings=True, convert_to_numpy=True ) def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--model_name_or_path', default="acge_text_embedding", type=str) parser.add_argument('--task_type', default=None, type=str) parser.add_argument('--pooling_method', default='cls', type=str) parser.add_argument('--output_dir', default='zh_results', type=str, help='output directory') parser.add_argument('--max_len', default=1024, type=int, help='max length') return parser.parse_args() if __name__ == '__main__': args = get_args() encoder = SentenceTransformer(args.model_name_or_path).half() encoder.encode = functools.partial(encoder.encode, normalize_embeddings=True) encoder.max_seq_length = int(args.max_len) task_names = [t.description["name"] for t in MTEB(task_types=args.task_type, task_langs=['zh', 'zh-CN']).tasks] TASKS_WITH_PROMPTS = ["T2Retrieval", "MMarcoRetrieval", "DuRetrieval", "CovidRetrieval", "CmedqaRetrieval", "EcomRetrieval", "MedicalRetrieval", "VideoRetrieval"] for task in task_names: evaluation = MTEB(tasks=[task], task_langs=['zh', 'zh-CN']) if task in TASKS_WITH_PROMPTS: evaluation.run(RetrievalModel(encoder), output_folder=args.output_dir, overwrite_results=False) else: evaluation.run(encoder, output_folder=args.output_dir, overwrite_results=False) ``` ## Usage #### acge 中文系列模型 在sentence-transformer库中的使用方法： ```python from sentence_transformers import SentenceTransformer sentences = ["数据1", "数据2"] model = SentenceTransformer('acge_text_embedding') print(model.max_seq_length) embeddings_1 = model.encode(sentences, normalize_embeddings=True) embeddings_2 = model.encode(sentences, normalize_embeddings=True) similarity = embeddings_1 @ embeddings_2.T print(similarity) ``` 在sentence-transformer库中的使用方法，选取不同的维度： ```python from sklearn.preprocessing import normalize from sentence_transformers import SentenceTransformer sentences = ["数据1", "数据2"] model = SentenceTransformer('acge_text_embedding') embeddings = model.encode(sentences, normalize_embeddings=False) matryoshka_dim = 1024 embeddings = embeddings[..., :matryoshka_dim] # Shrink the embedding dimensions embeddings = normalize(embeddings, norm="l2", axis=1) print(embeddings.shape) # => (2, 1024) ```